Models of Phonetic Recognition I: Issues That Arise in Attempting to Specify a Feature-Based Strategy For Speech Recognition

Authors

  • Dennis H. Klatt

Abstract

This is the first of e set of papers from the MIT Speech Communication Group expressing conflicting viewpoints as to the nature of the speech perception process and the best way to approach the problem of speech recognition by machine. In this paper, it is argued that all models employing phonetic feature detectors (whose purpose is to make phonetic decisions so as to reduce the information content of the input representation prior to lexical search) are suboptimal in a performance sense. Such models are usually incompletely specified, and they do not confront certain theoretical problems that are discussed here. It is suggested that the LAFS model of precompiled acoustic expectations for familiar words (Klatt, 1979) has theoretically superior characteristics. However, aspects of the Stevens model described in the next paper (in particular, relational invariance at the acoustic feature detector level) are an attractive candidate for the front-end processor of a next-generation LAFS strategy.

Downloads

Published

2022-12-03

How to Cite

1.
Klatt DH. Models of Phonetic Recognition I: Issues That Arise in Attempting to Specify a Feature-Based Strategy For Speech Recognition. Canadian Acoustics [Internet]. 2022 Dec. 3 [cited 2023 Feb. 8];14(3 bis):63-6. Available from: https://jcaa.caa-aca.ca/index.php/jcaa/article/view/3524

Issue

Vol. 14 No. 3 bis (1986): Montreal Symposium On Speech Recognition

Section

Proceedings of the Acoustics Week in Canada

License

Copyright on articles is held by the author(s). The corresponding author has the right to grant on behalf of all authors and does grant on behalf of all authors, a worldwide exclusive licence (or non-exclusive license for government employees) to the Publishers and its licensees in perpetuity, in all forms, formats and media (whether known now or created in the future)
i)    to publish, reproduce, distribute, display and store the Contribution;
ii)    to translate the Contribution into other languages, create adaptations, reprints, include within collections and create summaries, extracts and/or, abstracts of the Contribution;
iii)    to exploit all subsidiary rights in the Contribution,
iv)    to provide the inclusion of electronic links from the Contribution to third party material where-ever it may be located;
v)    to licence any third party to do any or all of the above.